A deep learning method for the prediction of 6-DoF ship motions in real conditions
Mingyang Zhang, Ghalib Taimuri, Jinfen Zhang, Spyros Hirdaris
Abstract
This paper presents a deep learning method for the prediction of ship motions in 6 Degrees of Freedom (DoF). Big data streams of Automatic Identification System (AIS), now-cast, and bathymetry records are used to extract motion trajectories and idealise environmental conditions. A rapid Fluid-Structure Interaction (FSI) model is used to generate ship motions that account for the influence of surrounding water and ship-controlling devices. A transformer neural network that accounts for the influence of operational conditions on ship dynamics is validated by learning the data streams corresponding to ship voyages and hydro-meteorological conditions between two ports in the Gulf of Finland. Predictions for a ship turning circle and motion dynamics between these two ports show that the proposed method can capture the influence of operational conditions on seakeeping and manoeuvring.